Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for occlusion detection of virtual and real objects

An occlusion detection and object technology, which is applied in the field of virtual and real object occlusion detection, can solve the problems of inflexible adaptive acquisition of foreground targets, and achieve the effect of automatic acquisition, optimization and flexible acquisition.

Active Publication Date: 2022-03-25
XIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a virtual and real object occlusion detection method, which realizes the automatic acquisition of the foreground image and solves the problem in the prior art that the adaptive acquisition of the foreground object in the moving image is not flexible.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for occlusion detection of virtual and real objects
  • A method for occlusion detection of virtual and real objects
  • A method for occlusion detection of virtual and real objects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0116] Step 1, such as figure 1 As shown, the first frame of image is modeled, and a background sample set is established for each pixel to realize the initialization of the background model; the initialization is completed by filling the sample set of pixels, but because only one frame of image cannot provide pixel space Distribution information, using similar spatial distribution characteristics of similar pixels, randomly selects the neighboring pixels of the processing pixel as its model sample value;

[0117] Specifically:

[0118] Step 1.1, establish the pixel model of the initial first frame image

[0119] M=f(x i ,y i )|(x i ,y i )∈N G (x,y) (1)

[0120] Among them, f(x i ,y i ) represents the value of the current pixel, N G (x, y) represents the adjacent pixel values ​​​​in the neighborhood; x i and y i are the two coordinates of pixel f;

[0121] Step 1.2, establish a background sample set for each pixel and initialize the background model

[0122] The ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a virtual and real object occlusion detection method, which is specifically implemented according to the following steps: step 1, modeling the first frame image, establishing a background sample set for each pixel, and realizing the initialization of the background model; step 2, performing the following steps The frame image adopts an adaptive method to judge the foreground target, and obtains the foreground image; step 3, updates the background model in step 1; step 4, uses median filtering to denoise the noise points in the foreground image obtained in step 2; Step 5, fill the hole area in the denoised foreground image in step 4 using the flood filling method; step 6, optimize the image processed in step 1-5, detect and remove the shadow area. The method for detecting occlusion of virtual and real objects in the present invention realizes the automatic acquisition of the foreground image, and solves the problem in the prior art that the adaptive acquisition of the foreground object in the moving image is not flexible.

Description

technical field [0001] The invention belongs to the technical field of combining computer graphics and virtual reality, and relates to a virtual and real object occlusion detection method. Background technique [0002] Occlusion detection between virtual and real objects is the key to virtual-real fusion, and virtual-real fusion is an important means to realize AR (Augmented Reality, Augmented Reality), and it is also the core difficulty in realizing the technology of merging virtual objects and real scenes based on real and virtual environments. With the wide application of augmented reality in fields including entertainment, life, military, education, traffic navigation, medicine and manufacturing, the problem of occlusion detection between virtual and real objects has become a bottleneck problem. [0003] The current research methods can be mainly divided into model-based methods, depth-based methods and image-based methods. The model-based method performs occlusion proc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/136G06T7/194G06T7/90G06T5/00
CPCG06T7/0002G06T7/136G06T7/194G06T7/90G06T2207/20032G06T5/70
Inventor 宁小娟王映辉赵艳妮张乐
Owner XIAN UNIV OF TECH